{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q6I5AHCHAUTWNYJ5FEIH5L4PBM","short_pith_number":"pith:Q6I5AHCH","canonical_record":{"source":{"id":"2410.09940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T17:51:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3603fbfc7e48c8875876a86f291cf810ad91f1cdfcd4b73aedda7e2d0deaa3b2","abstract_canon_sha256":"05e9a13f5c6de77d971a06021bcb98df7851afaaa1e37a04cd4307bba02a148e"},"schema_version":"1.0"},"canonical_sha256":"8791d01c47052766e13d29107eaf8f0b0ae456494712f4ae2ace2069f45df787","source":{"kind":"arxiv","id":"2410.09940","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09940","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09940v2","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09940","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"pith_short_12","alias_value":"Q6I5AHCHAUTW","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"pith_short_16","alias_value":"Q6I5AHCHAUTWNYJ5","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"pith_short_8","alias_value":"Q6I5AHCH","created_at":"2026-07-05T09:23:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q6I5AHCHAUTWNYJ5FEIH5L4PBM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09940","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T17:51:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3603fbfc7e48c8875876a86f291cf810ad91f1cdfcd4b73aedda7e2d0deaa3b2","abstract_canon_sha256":"05e9a13f5c6de77d971a06021bcb98df7851afaaa1e37a04cd4307bba02a148e"},"schema_version":"1.0"},"canonical_sha256":"8791d01c47052766e13d29107eaf8f0b0ae456494712f4ae2ace2069f45df787","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:14.484151Z","signature_b64":"oTHgKUTo0VW6kLhsABW6R+H6rEWvqsi+IXl0jVdnhF3LQ5VYbRVmw0aFC80XlqfBMvhog2jYUUhl74GDgSPSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8791d01c47052766e13d29107eaf8f0b0ae456494712f4ae2ace2069f45df787","last_reissued_at":"2026-07-05T09:23:14.483709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:14.483709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09940","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FkMPj8VaFiY6MjVlvO+WhSHWd6an2lLJgKtmLlbuF0jqMpeXv1mCGAIbIc2DsRm6WwPVv4AIfI5L11Qvgsp/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:34:34.973744Z"},"content_sha256":"a47925bb32c3d151512a2a410256be848db565f231a5387be0ddf2e8c80b5041","schema_version":"1.0","event_id":"sha256:a47925bb32c3d151512a2a410256be848db565f231a5387be0ddf2e8c80b5041"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q6I5AHCHAUTWNYJ5FEIH5L4PBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalized Group Data Attribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Ley, Gili Rusak, Himabindu Lakkaraju, Shichang Zhang, Suraj Srinivas","submitted_at":"2024-10-13T17:51:21Z","abstract_excerpt":"Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noisy label identification. However, existing DA methods are often computationally intensive, limiting their applicability to large-scale machine learning models. To address this challenge, we introduce the Generalized Group Data Attribution (GGDA) framework, which computationally simplifies DA by attributing to groups of training points instead of individual ones. GGDA is a general framework that subsumes existing attr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09940","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.09940/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbAyx6sjrTeJ/S8SKN+uK9gjCje73dRSzH++VMtSKKldA3DNv7nzSkMzmeaUq7G3hZWN8OcB+kJLLi35ljxQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T08:34:34.974643Z"},"content_sha256":"e9f0084950f00f1b94875b17ef841ba7a6cd1bbcc1b9f5f3b6722252a2bff98c","schema_version":"1.0","event_id":"sha256:e9f0084950f00f1b94875b17ef841ba7a6cd1bbcc1b9f5f3b6722252a2bff98c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM/bundle.json","state_url":"https://pith.science/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T08:34:34Z","links":{"resolver":"https://pith.science/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM","bundle":"https://pith.science/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM/bundle.json","state":"https://pith.science/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6I5AHCHAUTWNYJ5FEIH5L4PBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q6I5AHCHAUTWNYJ5FEIH5L4PBM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"05e9a13f5c6de77d971a06021bcb98df7851afaaa1e37a04cd4307bba02a148e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T17:51:21Z","title_canon_sha256":"3603fbfc7e48c8875876a86f291cf810ad91f1cdfcd4b73aedda7e2d0deaa3b2"},"schema_version":"1.0","source":{"id":"2410.09940","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09940","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09940v2","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09940","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"pith_short_12","alias_value":"Q6I5AHCHAUTW","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"pith_short_16","alias_value":"Q6I5AHCHAUTWNYJ5","created_at":"2026-07-05T09:23:14Z"},{"alias_kind":"pith_short_8","alias_value":"Q6I5AHCH","created_at":"2026-07-05T09:23:14Z"}],"graph_snapshots":[{"event_id":"sha256:e9f0084950f00f1b94875b17ef841ba7a6cd1bbcc1b9f5f3b6722252a2bff98c","target":"graph","created_at":"2026-07-05T09:23:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.09940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noisy label identification. However, existing DA methods are often computationally intensive, limiting their applicability to large-scale machine learning models. To address this challenge, we introduce the Generalized Group Data Attribution (GGDA) framework, which computationally simplifies DA by attributing to groups of training points instead of individual ones. GGDA is a general framework that subsumes existing attr","authors_text":"Dan Ley, Gili Rusak, Himabindu Lakkaraju, Shichang Zhang, Suraj Srinivas","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T17:51:21Z","title":"Generalized Group Data Attribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09940","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a47925bb32c3d151512a2a410256be848db565f231a5387be0ddf2e8c80b5041","target":"record","created_at":"2026-07-05T09:23:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"05e9a13f5c6de77d971a06021bcb98df7851afaaa1e37a04cd4307bba02a148e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T17:51:21Z","title_canon_sha256":"3603fbfc7e48c8875876a86f291cf810ad91f1cdfcd4b73aedda7e2d0deaa3b2"},"schema_version":"1.0","source":{"id":"2410.09940","kind":"arxiv","version":2}},"canonical_sha256":"8791d01c47052766e13d29107eaf8f0b0ae456494712f4ae2ace2069f45df787","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8791d01c47052766e13d29107eaf8f0b0ae456494712f4ae2ace2069f45df787","first_computed_at":"2026-07-05T09:23:14.483709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:14.483709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oTHgKUTo0VW6kLhsABW6R+H6rEWvqsi+IXl0jVdnhF3LQ5VYbRVmw0aFC80XlqfBMvhog2jYUUhl74GDgSPSBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:14.484151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09940","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a47925bb32c3d151512a2a410256be848db565f231a5387be0ddf2e8c80b5041","sha256:e9f0084950f00f1b94875b17ef841ba7a6cd1bbcc1b9f5f3b6722252a2bff98c"],"state_sha256":"c7981c5f4213c0c45e24f7d97d5d41c544cd3831d2dd9182a35d6f379557c25b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BRfz0sgtTYkWeamkDyNEClBlfXXwhuI+SWOmuHEGzE7ixNU0Bkay8moa7Pf0tlVC6KW8jniAEVvPAZYAqFdyAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T08:34:34.980942Z","bundle_sha256":"ac67803f12b3d71fa7bd45f82d76b8017c3d3e7abf9e340eda72fac835f942e7"}}